Integration

Feedbin integration

Feedbin is a paid RSS, Atom and JSON Feed reader. Subscribe to and unsubscribe from feeds, read entries (all, per feed, unread, starred, updated, recently read, or by id with full HTML content), mark entries as read, star entries, list tags applied to feeds and feed icons, and create, run, rename and delete saved searches. Unread, starred, updated, recently read and saved-search tools return entry ids only: fetch the entries with list_entries (up to 100 ids per call). Renaming feeds, marking entries unread, unstarring, creating or deleting tags, the credential check, OPML imports and pages are not exposed. Authentication is HTTP Basic with the Feedbin account email and password.

Connect Feedbin How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Feedbin.Built from the 21 Feedbin tools below, on the connection you add once.

What you can do with Feedbin

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Saved search, 5 operations

create_saved_searchCreate saved searchPOSTCreates a saved search from a name and a Feedbin search query, and returns it with its id, name and query.
delete_saved_searchDelete saved searchDELETEDeletes a saved search. Returns 204 with no body, 403 when the user does not own it.
get_saved_search_resultsGet saved search resultsGETReturns the ids of the entries matching a saved search, in order. Fetch them with list_entries (ids). 403 when the user does not own the search.
list_saved_searchesList saved searchesGETReturns all saved searches with their id, name and query.
update_saved_searchUpdate saved searchPATCHRenames a saved search and returns it with its id, name and query.

Subscription, 4 operations

create_subscriptionCreate subscriptionPOSTSubscribes to a feed. feed_url may be the feed URL or the website URL. When the site exposes several feeds the API answers 300 with the list of feed_url and title choices.
delete_subscriptionDelete subscriptionDELETEUnsubscribes from the feed of this subscription. Returns 204 with no body, 403 when the user does not own it.
get_subscriptionGet subscriptionGETReturns one subscription: id, feed_id, title, feed_url, site_url and created_at. 403 when the user does not own it.
list_subscriptionsList subscriptionsGETReturns all the feeds the user is subscribed to, with their subscription id, feed_id, title, feed_url and site_url.

Entry, 3 operations

get_entryGet entryGETReturns one entry with its title, author, url, HTML content, summary and dates. 404 when it does not exist, 403 when the user does not subscribe to its feed.
list_entriesList entriesGETReturns a page of the user's entries, newest first (created_at descending). Filter with read, starred, since or ids (up to 100 ids, as returned by list_unread_entries).
list_feed_entriesList feed entriesGETReturns a page of the entries of one feed. Supports the same filters as list_entries except ids.

Starred entry, 2 operations

list_starred_entriesList starred entriesGETReturns the ids of all starred entries (ids only). Fetch the entries with list_entries, passing up to 100 ids at a time.
star_entriesStar entriesPOSTStars entries (at most 1,000 ids per call) and returns the ids that were starred. A missing id usually means the user no longer has access to its feed.

Tagging, 2 operations

get_taggingGet taggingGETReturns one tagging (id, feed_id and tag name). 403 when the user does not own it.
list_taggingsList taggingsGETReturns every tagging: which tag name is applied to which feed_id.

Unread entry, 2 operations

list_unread_entriesList unread entriesGETReturns the ids of all unread entries (ids only). Fetch the entries with list_entries, passing up to 100 ids at a time.
mark_entries_readMark entries readPOSTMarks entries as read (at most 1,000 ids per call) and returns the ids that were marked. A missing id usually means the user no longer has access to its feed.

Icon, 1 operation

list_iconsList iconsGETReturns the favicon of every subscribed feed's host, resized to at most 32x32. A host with no icon is missing from the list.

Recently read entry, 1 operation

list_recently_read_entriesList recently read entriesGETReturns the ids of the entries the user read recently (on Feedbin, an entry viewed for 10 seconds). Fetch the entries with list_entries (ids).

Updated entry, 1 operation

list_updated_entriesList updated entriesGETReturns the ids of entries modified after they were first published. Read the changes with list_entries (ids, include_original, include_content_diff).

Use Feedbin from Claude Code, Cursor or Codex

Connect Feedbin in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Feedbin operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Feedbin

Create your workspace
Sign up free. Nothing to install.
Connect Feedbin once
Add your Feedbin connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.